Feature

.github/workflows/deploy_prd.yml

@@ -4,7 +4,7 @@ on:
   workflow_dispatch:
   push:
     branches:
-      - main
+      - prod
 
 jobs:
   deploy-prd:
@@ -35,21 +35,21 @@ jobs:
 
       - name: Validar bundle Databricks
         env:
-          DATABRICKS_CONFIG_PROFILE: PRD
+          DATABRICKS_CONFIG_PROFILE: PROD
         run: |
-          cd dab_treinamento
-          databricks bundle validate --target prd
+          cd dab_test
+          databricks bundle validate --target prod
 
       - name: Deploy bundle Databricks
         env:
-          DATABRICKS_CONFIG_PROFILE: PRD
+          DATABRICKS_CONFIG_PROFILE: PROD
         run: |
-          cd dab_treinamento
-          databricks bundle deploy --target prd
+          cd dab_test
+          databricks bundle deploy --target prod
 
       - name: Executar job Databricks
         env:
-          DATABRICKS_CONFIG_PROFILE: PRD
+          DATABRICKS_CONFIG_PROFILE: PROD
         run: |
-          cd dab_treinamento
-          databricks bundle run dab_treinamento_job --target prd
+          cd dab_test
+          databricks bundle run dab_test_job --target prod

README.md

@@ -0,0 +1 @@
+# repositorio-teste video - p

dab_test/.vscode/__builtins__.pyi

@@ -0,0 +1,3 @@
+# Typings for Pylance in Visual Studio Code
+# see https://github.com/microsoft/pyright/blob/main/docs/builtins.md
+from databricks.sdk.runtime import *

dab_test/.vscode/extensions.json

@@ -0,0 +1,7 @@
+{
+    "recommendations": [
+        "charliermarsh.ruff",
+        "databricks.databricks",
+        "redhat.vscode-yaml"
+    ]
+}

dab_test/.vscode/settings.json

@@ -0,0 +1,39 @@
+{
+    "jupyter.interactiveWindow.cellMarker.codeRegex": "^# COMMAND ----------|^# Databricks notebook source|^(#\\s*%%|#\\s*\\<codecell\\>|#\\s*In\\[\\d*?\\]|#\\s*In\\[ \\])",
+    "jupyter.interactiveWindow.cellMarker.default": "# COMMAND ----------",
+    "python.testing.pytestArgs": [
+        "."
+    ],
+    "files.exclude": {
+        "**/*.egg-info": true,
+        "**/__pycache__": true,
+        ".pytest_cache": true,
+        "dist": true,
+    },
+    "files.associations": {
+        "**/.gitkeep": "markdown"
+    },
+
+    // Pylance settings (VS Code)
+    // Set typeCheckingMode to "basic" to enable type checking!
+    "python.analysis.typeCheckingMode": "off",
+    "python.analysis.extraPaths": ["src", "lib", "resources"],
+    "python.analysis.diagnosticMode": "workspace",
+    "python.analysis.stubPath": ".vscode",
+
+    // Pyright settings (Cursor)
+    // Set typeCheckingMode to "basic" to enable type checking!
+    "cursorpyright.analysis.typeCheckingMode": "off",
+    "cursorpyright.analysis.extraPaths": ["src", "lib", "resources"],
+    "cursorpyright.analysis.diagnosticMode": "workspace",
+    "cursorpyright.analysis.stubPath": ".vscode",
+
+    // General Python settings
+    "python.defaultInterpreterPath": "./.venv/bin/python",
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true,
+    "[python]": {
+        "editor.defaultFormatter": "charliermarsh.ruff",
+        "editor.formatOnSave": true,
+    },
+}

dab_test/AGENTS.md

@@ -0,0 +1,25 @@
+# Declarative Automation Bundles Project
+
+This project uses Declarative Automation Bundles (DABs) for deployment. Add project-specific instructions below.
+
+## For AI Agents: Use Databricks AI Tools
+
+**BEFORE any other action, read the `databricks-core` skill.**
+
+It sets you up to work with this project reliably: CLI authentication, profile
+selection, data discovery, and the bundle deployment workflow. Without it,
+results are often slower and less accurate.
+
+If this skill is not available (Databricks AI Tools are not installed), you can install them for your coding agent in seconds:
+
+```bash
+databricks aitools install
+```
+
+If the CLI is not installed, see: https://docs.databricks.com/dev-tools/cli/install
+
+---
+
+## Project Instructions
+
+<!-- Add your project-specific instructions, coding conventions, or notes here -->

dab_test/CLAUDE.md

@@ -0,0 +1,6 @@
+# CLAUDE.md
+
+Project guidance for AI agents lives in AGENTS.md.
+Claude Code loads it via the import below.
+
+@AGENTS.md

dab_test/README.md

@@ -0,0 +1,71 @@
+# dab_test
+
+The 'dab_test' project was generated by using the default-python template.
+
+* `src/`: Python source code for this project.
+  * `src/dab_test/`: Shared Python code that can be used by jobs and pipelines.
+* `resources/`:  Resource configurations (jobs, pipelines, etc.)
+* `tests/`: Unit tests for the shared Python code.
+* `fixtures/`: Fixtures for data sets (primarily used for testing).
+
+
+## Getting started
+
+Choose how you want to work on this project:
+
+(a) Directly in your Databricks workspace, see
+    https://docs.databricks.com/dev-tools/bundles/workspace.
+
+(b) Locally with an IDE like Cursor or VS Code, see
+    https://docs.databricks.com/dev-tools/vscode-ext.html.
+
+(c) With command line tools, see https://docs.databricks.com/dev-tools/cli/databricks-cli.html
+
+If you're developing with an IDE, dependencies for this project should be installed using uv:
+
+*  Make sure you have the UV package manager installed.
+   It's an alternative to tools like pip: https://docs.astral.sh/uv/getting-started/installation/.
+*  Run `uv sync --dev` to install the project's dependencies.
+
+
+# Using this project using the CLI
+
+The Databricks workspace and IDE extensions provide a graphical interface for working
+with this project. It's also possible to interact with it directly using the CLI:
+
+1. Authenticate to your Databricks workspace, if you have not done so already:
+    ```
+    $ databricks configure
+    ```
+
+2. To deploy a development copy of this project, type:
+    ```
+    $ databricks bundle deploy --target dev
+    ```
+    (Note that "dev" is the default target, so the `--target` parameter
+    is optional here.)
+
+    This deploys everything that's defined for this project.
+    For example, the default template would deploy a pipeline called
+    `[dev yourname] dab_test_etl` to your workspace.
+    You can find that resource by opening your workpace and clicking on **Jobs & Pipelines**.
+
+3. Similarly, to deploy a production copy, type:
+   ```
+   $ databricks bundle deploy --target prod
+   ```
+   Note the default template has a includes a job that runs the pipeline every day
+   (defined in resources/sample_job.job.yml). The schedule
+   is paused when deploying in development mode (see
+   https://docs.databricks.com/dev-tools/bundles/deployment-modes.html).
+
+4. To run a job or pipeline, use the "run" command:
+   ```
+   $ databricks bundle run
+   ```
+
+5. Finally, to run tests locally, use `pytest`:
+   ```
+   $ uv run pytest
+   ```
+video 01

dab_test/databricks.yml

@@ -0,0 +1,51 @@
+# This is a Declarative Automation Bundle definition for dab_test.
+# See https://docs.databricks.com/dev-tools/bundles/index.html for documentation.
+bundle:
+  name: dab_test
+  uuid: 348afa13-f395-4806-9fcf-f5fc52935756
+
+include:
+  - resources/jobs/*.yml
+  - resources/pipelines/*.yml
+  - resources/schemas/*.yml
+
+artifacts:
+  python_artifact:
+    type: whl
+    build: uv build --wheel
+
+# Variable declarations. These variables are assigned in the dev/prod targets below.
+variables:
+  catalog:
+    description: The catalog to use
+  schema:
+    description: The schema to use
+  catalog_name:
+    description: "Catalog used by the job"
+    default: dev
+  performance_target:
+    description: "Performance target for the job"
+    default: "STANDARD"
+targets:
+  dev:
+    # The default target uses 'mode: development' to create a development copy.
+    # - Deployed resources get prefixed with '[dev my_user_name]'
+    # - Any job schedules and triggers are paused by default.
+    # See also https://docs.databricks.com/dev-tools/bundles/deployment-modes.html.
+    mode: development
+    default: true
+    workspace:
+      host: https://dbc-39ee3252-8e93.cloud.databricks.com
+    variables:
+      catalog: dev
+      schema: rescue_b
+  prod:
+    mode: production
+    workspace:
+      host: https://dbc-39ee3252-8e93.cloud.databricks.com
+    variables:
+      catalog: prod
+      schema: rescue_b
+    permissions:
+      - user_name: rubencruzh@gmail.com
+        level: CAN_MANAGE

dab_test/fixtures/.gitkeep

@@ -0,0 +1,9 @@
+# Test fixtures directory
+
+Add JSON or CSV files here. In tests, use them with `load_fixture()`:
+
+```
+def test_using_fixture(load_fixture):
+    data = load_fixture("my_data.json")
+    assert len(data) >= 1
+```

dab_test/pyproject.toml

@@ -0,0 +1,36 @@
+[project]
+name = "dab_test"
+version = "0.0.1"
+authors = [{ name = "rubencruzh@gmail.com" }]
+requires-python = ">=3.10,<3.13"
+dependencies = [
+    # Any dependencies for jobs and pipelines in this project can be added here
+    # See also https://docs.databricks.com/dev-tools/bundles/library-dependencies
+    #
+    # LIMITATION: for pipelines, dependencies are cached during development;
+    # add dependencies to the 'environment' section of your pipeline.yml file instead
+]
+
+[dependency-groups]
+dev = [
+    "pytest",
+    "ruff",
+    "pyyaml",
+    "databricks-dlt",
+    "databricks-connect>=15.4,<15.5",
+    "ipykernel",
+]
+
+[project.scripts]
+main = "dab_test.main:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/dab_test"]
+
+[tool.ruff]
+line-length = 120

dab_test/resources/jobs/dab_test_job.yml

@@ -0,0 +1,36 @@
+# Job do treinamento para executar o notebook demo.
+resources:
+  jobs:
+    dab_test_job:
+      name: dab_test_job
+      tags:
+        treinamento: dab
+        ambiente: dev
+        area: engenharia
+      description: Job de treinamento que ingere usuários de exemplo com parâmetros dinâmicos.
+      parameters:
+        - name: catalog_name
+          default: ${var.catalog_name}
+        - name: user_id
+          default: "3"
+        - name: user_name
+          default: "Anselmo"
+      email_notifications:
+        on_failure:
+          - rubencruzh@gmail.com
+      timeout_seconds: 900
+      schedule:
+        quartz_cron_expression: "0 0 8 ? * TUE *"
+        timezone_id: America/Sao_Paulo
+      tasks:
+        - task_key: ingestao_usuarios
+          description: Ingestão de usuários de exemplo via notebook.
+          notebook_task:
+            notebook_path: ../../src/notebooks/demo_notebook.py
+            base_parameters:
+              catalog_name: "{{job.parameters.catalog_name}}"
+              user_id: "{{job.parameters.user_id}}"
+              user_name: "{{job.parameters.user_name}}"
+      queue:
+        enabled: true
+      performance_target: ${var.performance_target}

dab_test/src/dab_test/main.py

@@ -0,0 +1,14 @@
+from databricks.sdk.runtime import spark
+from pyspark.sql import DataFrame
+
+
+def find_all_taxis() -> DataFrame:
+    return spark.read.table("samples.nyctaxi.trips")
+
+
+def main():
+    find_all_taxis().show(5)
+
+
+if __name__ == "__main__":
+    main()

dab_test/src/notebooks/demo_notebook.py

@@ -0,0 +1,30 @@
+# Databricks notebook source
+# DBTITLE 1,Configura widgets de entrada
+dbutils.widgets.text("catalog", "dev", "Catalog Name")
+dbutils.widgets.text("user_id", "3", "User ID")
+dbutils.widgets.text("user_name", "Anselmo", "User Name")
+
+# COMMAND ----------
+# DBTITLE 1,Obtém valores informados
+catalog_name = dbutils.widgets.get("catalog")
+user_id = int(dbutils.widgets.get("user_id"))
+user_name = dbutils.widgets.get("user_name")
+print(f"Using Catalog: {catalog_name}")
+print(f"Inserting user_id={user_id}, user_name={user_name}")
+
+# COMMAND ----------
+# DBTITLE 1,Cria tabela e insere dados de exemplo + parâmetro
+spark.sql(
+    f"CREATE TABLE IF NOT EXISTS {catalog_name}.rescue_b.users (id INT, name STRING)"
+)
+spark.sql(
+    f"INSERT OVERWRITE {catalog_name}.rescue_b.users VALUES (1, 'Alice'), (2, 'Bob')"
+)
+spark.sql(
+    f"INSERT INTO {catalog_name}.rescue_b.users VALUES ({user_id}, '{user_name}')"
+)
+
+# COMMAND ----------
+# DBTITLE 1,Lê os dados inseridos
+result_df = spark.sql(f"SELECT * FROM {catalog_name}.rescue_b.users ORDER BY id")
+display(result_df)